diff options
| author | Douglas Hanley <thesecretaryofwar@gmail.com> | 2024-06-21 00:38:22 -0500 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-06-21 08:38:22 +0300 |
| commit | 80ea089d771f0c2d97afa8bead80ded412f600d7 (patch) | |
| tree | 25c04a967b5913ffdc00d1a851dcfbeb9ab37a37 /unicode.cpp | |
| parent | 0e64591e8290037db6412665a56354b789a0597e (diff) | |
llama : allow pooled embeddings on any model (#7477)
* create append_pooling operation; allow to specify attention_type; add last token pooling; update examples
* find result_norm/result_embd tensors properly; update output allocation logic
* only use embd output for pooling_type NONE
* get rid of old causal_attn accessor
* take out attention_type; add in llama_set_embeddings
* bypass logits when doing non-NONE pooling
Diffstat (limited to 'unicode.cpp')
0 files changed, 0 insertions, 0 deletions